The U.S. Navy is bolstering its artificial intelligence capabilities to improve detection of Iranian naval mines in the Strait of Hormuz, according to a recently awarded contract. The strategic waterway is a major artery for oil shipments, and disruptions there pose growing risks to international trade and economic stability.
President Donald Trump has stated that the U.S. Navy is engaged in clearing Iranian mines from the strait. Despite a tenuous ceasefire in the weeks-long conflict between the United States and Iran, the process of sweeping for underwater explosives can be slow and could take months to complete.
To accelerate that work, the Navy has expanded its relationship with Domino Data Lab, a San Francisco-based artificial intelligence company. The award, described as up to $99.7 million, is intended to deepen Domino’s role as the AI infrastructure for Project AMMO - Accelerated Machine Learning for Maritime Operations. Earlier references to the contract framed it as up to $100 million.
Project AMMO seeks to make detection of underwater mines faster and more reliable while reducing the degree of human intervention required. Domino’s software ingests and unifies data from multiple sensor types, including side-scan sonar and visual imaging systems. It also provides tools for the Navy to observe how different AI detection models perform when deployed, to spot underperformance or failures, and to push updates intended to improve detection accuracy.
Domino’s executives emphasize speed as the central benefit. Before Domino’s involvement, updating the AI models that run on unmanned underwater vehicles - or UUVs - to recognize previously unseen mine types could take as long as six months. Domino says it has shortened that update cycle to a matter of days.
"Mine-hunting used to be a job for ships," said Thomas Robinson, Domino’s chief operating officer. "It’s becoming a job for AI. The Navy is paying for the platform that lets it train, govern, and field that AI at a speed required for contested waters that block global trade and imperil sailors."
Robinson provided a concrete example of the speed advantage: if UUVs had been trained on Russian mines in the Baltic Sea but needed to be redeployed to the Strait of Hormuz to detect Iranian mines, he said the Navy could be ready in a week rather than a year using Domino’s tools.
A Navy spokesman was not immediately available to comment.
Contextual implications
- Faster AI updates for UUVs could reduce the calendar time required for mine-clearing operations in contested waters.
- Shortened model retraining cycles aim to make detection systems more adaptive to new or previously unseen mine types.
- The effort centers on integrating heterogeneous sensor inputs and operational monitoring to permit rapid corrections to detection models in the field.